Update README.md

README.md

@@ -18,4 +18,19 @@ alt="drawing" width="400"/>
 <!-- description start -->
 ## Description
 This repo contains GGUF format model files for [Trendyol's Trendyol LLM 7b base v0.1](https://huggingface.co/Trendyol/Trendyol-LLM-7b-base-v0.1)
-<!-- description end -->
+<!-- description end -->
+
+# Quantization methods
+| quantization method | bits | size     | use case                                            | recommended |
+|---------------------|------|----------|-----------------------------------------------------|-------------|
+| Q2_K                | 2    | 2.59 GB  | smallest, significant quality loss - not recommended for most purposes | ❌         |
+| Q3_K_S              | 3    | 3.01 GB  | very small, high quality loss                       | ❌         |
+| Q3_K_M              | 3    | 3.36 GB  | very small, high quality loss                       | ❌         |
+| Q3_K_L              | 3    | 3.66 GB  | small, substantial quality loss                     | ❌         |
+| Q4_0                | 4    | 3.9 GB  | legacy; small, very high quality loss - prefer using Q3_K_M | ❌         |
+| Q4_K_M              | 4    | 4.15 GB  | medium, balanced quality - recommended              | ✅         |
+| Q5_0                | 5    | 4.73 GB  | legacy; medium, balanced quality - prefer using Q4_K_M | ❌         |
+| Q5_K_S              | 5    | 4.73 GB  | large, low quality loss - recommended               | ✅         |
+| Q5_K_M              | 5    | 4.86 GB  | large, very low quality loss - recommended          | ✅         |
+| Q6_K                | 6    | 5.61 GB  | very large, extremely low quality loss              | ❌         |
+| Q8_0                | 8    | 13.7 GB  | very large, extremely low quality loss - not recommended | ❌         |